Radiomics Features Predict Telomerase Reverse Transcriptase Promoter Mutations in World Health Organization Grade II Gliomas via a Machine-Learning Approach

Shengyu Fang; Ziwen Fan; Zhiyan Sun; Yiming Li; Xing Liu; Yuchao Liang; Yukun Liu; Chunyao Zhou; Qiang Zhu; Hong Zhang; Tianshi Li; Shaowu Li; Tao Jiang; Yinyan Wang; Lei Wang

doi:10.3389/fonc.2020.606741

Radiomics Features Predict Telomerase Reverse Transcriptase Promoter Mutations in World Health Organization Grade II Gliomas via a Machine-Learning Approach

Front Oncol. 2021 Feb 11:10:606741. doi: 10.3389/fonc.2020.606741. eCollection 2020.

Authors

Shengyu Fang¹, Ziwen Fan², Zhiyan Sun¹, Yiming Li², Xing Liu³, Yuchao Liang², Yukun Liu², Chunyao Zhou², Qiang Zhu², Hong Zhang², Tianshi Li², Shaowu Li⁴, Tao Jiang^{1

2}, Yinyan Wang^{1

2}, Lei Wang²

Affiliations

¹ Beijing Neurosurgical Institute, Capital Medical University, Beijing, China.
² Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
³ Department of Pathology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.
⁴ Department of Neuroradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.

Abstract

The detection of mutations in telomerase reverse transcriptase promoter (pTERT) is important since preoperative diagnosis of pTERT status helps with evaluating prognosis and determining the surgical strategy. Here, we aimed to establish a radiomics-based machine-learning algorithm and evaluated its performance with regard to the prediction of mutations in pTERT in patients with World Health Organization (WHO) grade II gliomas. In total, 164 patients with WHO grade II gliomas were enrolled in this retrospective study. We extracted a total of 1,293 radiomics features from multi-parametric magnetic resonance imaging scans. Elastic net (used for feature selection) and support vector machine with linear kernel were applied in nested 10-fold cross-validation loops. The predictive model was evaluated by receiver operating characteristic and precision-recall analyses. We performed an unpaired t-test to compare the posterior predictive probabilities among patients with differing pTERT statuses. We selected 12 valuable radiomics features using nested 10-fold cross-validation loops. The area under the curve (AUC) was 0.8446 (95% confidence interval [CI], 0.7735-0.9065) with an optimal summed value of sensitivity of 0.9355 (95% CI, 0.8802-0.9788) and specificity of 0.6197 (95% CI, 0.5071-0.7371). The overall accuracy was 0.7988 (95% CI, 0.7378-0.8598). The F1-score was 0.8406 (95% CI, 0.7684-0.902) with an optimal precision of 0.7632 (95% CI, 0.6818-0.8364) and recall of 0.9355 (95% CI, 0.8802-0.9788). Posterior probabilities of pTERT mutations were significantly different between patients with wild-type and mutant TERT promoters. Our findings suggest that a radiomics analysis with a machine-learning algorithm can be useful for predicting pTERT status in patients with WHO grade II glioma and may aid in glioma management.

Keywords: TERT promoter mutation; low-grade glioma; machine-learning; nested cross-validation; radiomics.